The discovery of new electrocatalysts can be aided by density functional theory (DFT) computation of overpotentials based on the energies of chemical intermediates on prospective adsorption sites. We hypothesize that when training a machine learning model on DFT data, one could improve accuracy by introducing a quantitative measure of similarity among adsorption sites. When we augment a graph neural network-based machine learning workflow using similarity as an input feature, we find that the required training dataset size is decreased from 1,600 to 800, leading to a 2× acceleration: the number of DFT calculations required to train to a given level of accuracy is cut in half. This approach identifies Fe0.125Co0.125Ni0.229Ir0.229Ru0.292 as a promising oxygen reduction reaction catalyst with an overpotential of 0.24 V, outperforming a Pt/C benchmark. We examine, by studying experimentally four additional HEAs, the predictive power of the computational approach.

中文翻译：

---

使用机器学习筛选的高熵合金电催化剂，该催化剂由量子启发的相似性分析提供信息


密度泛函理论 （DFT） 基于潜在吸附位点上化学中间体的能量计算过电位可以帮助发现新的电催化剂。我们假设，当在 DFT 数据上训练机器学习模型时，可以通过引入吸附位点之间相似性的定量测量来提高准确性。当我们使用相似性作为输入特征来增强基于图神经网络的机器学习工作流程时，我们发现所需的训练数据集大小从 1,600 减少到 800，从而加快了 2×：训练到给定精度水平所需的 DFT 计算数量减少了一半。该方法将 Fe0.125Co0.125Ni0.229Ir0.229Ru0.292 确定为一种很有前途的氧还原反应催化剂，具有 0.24 V 的过电位，优于 Pt/C 基准。我们通过实验研究另外四种 HEA 来检查计算方法的预测能力。